Self-adaptive scheduling method based on hydraulic model and AI algorithm and related device

Abstract

The invention discloses an adaptive scheduling method based on a hydraulic model and an AI algorithm and a related device, and the method comprises the steps: carrying out the water prediction based on the current water consumption through employing an SARIMAX model, obtaining the predicted water consumption, selecting a scheme from a scheme library based on the current water consumption, the predicted water consumption and the current working condition information of a water plant, and obtaining a first scheme set, determining a second scheme set based on the first scheme set and a genetic annealing algorithm, determining a first result set by using a pipe network hydraulic model based on the second scheme set, selecting schemes from a scheme library based on the first result set to obtain a third scheme set, and determining a fourth scheme set based on the third scheme set and the genetic annealing algorithm, based on the first result set and the fourth scheme set, a pump room hydraulic model is used for determining a second result set, a water supply scheduling scheme is determined based on the first result set, the second result set and a target function, and the target water supply scheduling scheme is used for self-adaptive water supply scheduling. The safety and the stability of water supply dispatching can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of water supply scheduling, and specifically to an adaptive scheduling method and related devices based on a hydraulic model and an AI algorithm. Background Art

[0002] Water supply refers to the provision of water resources through public facilities, commercial organizations, community efforts or individuals. Water is usually delivered through pumps and pipes. At present, when supplying water, big data and intelligent algorithms are used as theories to predict the water supply scheduling plan for a period of time in the future. Since the water supply scheduling plan is determined offline based on historical data, the accuracy of the determined water supply scheduling plan is low, and the safety and stability of water supply scheduling cannot be guaranteed. Summary of the invention

[0003] The embodiments of the present application disclose an adaptive scheduling method and related devices based on a hydraulic model and an AI algorithm, which are used to improve the accuracy of a water supply scheduling scheme, thereby improving the safety and stability of the water supply scheduling.

[0004] In a first aspect, the present application discloses an adaptive scheduling method based on a hydraulic model and an AI algorithm, including: Get the current water consumption; Based on the current water consumption, a SARIMAX model is used to predict water consumption to obtain predicted water consumption; Based on the current water consumption, the predicted water consumption and the current water plant operating condition information, a water pressure scheduling scheme is selected from a scheme library to obtain a first scheme set; Based on the first solution set, a genetic annealing algorithm is used to determine a water outlet pressure scheduling solution to obtain a second solution set; Based on the second solution set, the pipeline network information and water plant information are determined using the pipeline network hydraulic model to obtain a first result set; Selecting a pump room scheduling solution from the solution library based on the first result set to obtain a third solution set; Determine the pump room scheduling solution based on the third solution set using a genetic annealing algorithm to obtain a fourth solution set; Determine a pump room scheduling solution using a pump room hydraulic model based on the first result set and the fourth solution set to obtain a second result set; A target water supply scheduling scheme is determined based on the first result set, the second result set and an objective function, and the target water supply scheduling scheme is used to perform adaptive water supply scheduling.

[0005] In a second aspect, the embodiment of the present application discloses an adaptive scheduling device based on a hydraulic model and an AI algorithm, comprising: An acquisition unit, used for acquiring current water consumption; A prediction unit, configured to use a SARIMAX model to predict water consumption based on the current water consumption to obtain predicted water consumption; A selection unit, configured to select a water pressure scheduling scheme from a scheme library based on the current water consumption, the predicted water consumption and the current water plant operating condition information to obtain a first scheme set; A determination unit, configured to determine a water outlet pressure scheduling scheme based on the first scheme set by using a genetic annealing algorithm to obtain a second scheme set; The determining unit is further configured to determine the pipe network information and the water plant information using the pipe network hydraulic model based on the second solution set to obtain a first result set; The selection unit is further configured to select a pump room scheduling solution from the solution library based on the first result set to obtain a third solution set; The determining unit is further used to determine the pump room scheduling scheme based on the third scheme set using a genetic annealing algorithm to obtain a fourth scheme set; The determining unit is further used to determine the pump room scheduling solution using the pump room hydraulic model based on the first result set and the fourth solution set to obtain a second result set; The determination unit is further used to determine a target water supply scheduling scheme based on the first result set, the second result set and the objective function, and the target water supply scheduling scheme is used to perform adaptive water supply scheduling.

[0006] In a third aspect, an embodiment of the present application discloses a server, including a processor and a memory, wherein the processor is used to call a computer program stored in the memory to execute the method disclosed in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, on which a computer program or computer instructions are stored. When the computer program or computer instructions are executed by a processor, the method disclosed in the first aspect above is implemented.

[0008] In a fifth aspect, an embodiment of the present application discloses a computer program product, which includes a computer program code. When the computer program code is executed by a processor, the above method is executed.

[0009] In an embodiment of the present application, the server obtains the current water consumption, uses the SARIMAX model to predict the water consumption based on the current water consumption to obtain the predicted water consumption, selects a water supply scheduling scheme from the scheme library based on the current water consumption, the predicted water consumption and the current water plant operating condition information to obtain a first scheme set, determines the water outlet pressure scheduling scheme based on the first scheme set using a genetic annealing algorithm to obtain a second scheme set, determines the pipeline information and water plant information based on the second scheme set using a pipeline hydraulic model to obtain a first result set, selects a pump room scheduling scheme from the scheme library based on the first result set to obtain a third scheme set, determines the pump room scheduling scheme based on the third scheme set using a genetic annealing algorithm to obtain a fourth scheme set, determines the pump room scheduling scheme based on the first result set and the fourth scheme set using a pump room hydraulic model to obtain a second result set, determines a target water supply scheduling scheme based on the first result set, the second result set and the objective function, and the target water supply scheduling scheme is used to perform adaptive water supply scheduling. It can be seen that the server can use the current water consumption and the current water plant operating condition information to determine the water supply scheduling plan. Since the real-time water consumption and the real-time water plant operating condition information are used to determine the online water supply scheduling plan, the accuracy of the determined water supply scheduling plan can be improved, thereby improving the safety and stability of the water supply scheduling, as well as the accuracy of the adaptive water supply scheduling. In addition, since the genetic annealing algorithm is used in the process of determining the water supply scheduling plan, the stability and determination efficiency of the water supply scheduling plan can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 It is a flow chart of an adaptive scheduling method based on a hydraulic model and an AI algorithm disclosed in an embodiment of the present application; Figure 2 It is a flow chart of another adaptive scheduling method based on hydraulic model and AI algorithm disclosed in the embodiment of the present application; Figure 3 It is a structural schematic diagram of an adaptive scheduling device based on a hydraulic model and an AI algorithm disclosed in an embodiment of the present application; Figure 4 It is a structural diagram of a server disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0013] The embodiment of the present application discloses an adaptive scheduling method and related devices based on a hydraulic model and an AI algorithm, which are used to improve the accuracy of a water supply scheduling scheme, thereby improving the safety and stability of water supply scheduling. Detailed descriptions are given below.

[0014] See also Figure 1 , Figure 1 is a flow chart of an adaptive scheduling method based on a hydraulic model and an AI algorithm disclosed in an embodiment of the present application. The adaptive scheduling method based on a hydraulic model and an AI algorithm can be applied to a server. Figure 1 As shown, the adaptive scheduling method based on hydraulic model and AI algorithm may include the following steps.

[0015] 101. Get the current water consumption.

[0016] The server may obtain the current water consumption in real time, periodically or regularly. The current water consumption may be the water consumption at the current moment.

[0017] The range of the current water consumption obtained varies depending on the water supply range of the water supply scheduling plan. For example, when a water supply scheduling plan is determined for a city, the current water consumption obtained is the current water consumption of the city. When a water supply scheduling plan is determined for a community, the current water consumption obtained is the current water consumption of the community.

[0018] 102. Based on the current water consumption, the SARIMAX model is used to predict the water consumption to obtain the predicted water consumption.

[0019] After the server obtains the current water consumption, it can perform a water consumption prediction based on the current water consumption to obtain the predicted water consumption. It can be seen that the future water consumption can be predicted based on the current water consumption.

[0020] In some embodiments, the server may obtain weather information and holiday information, and may use a water quantity prediction algorithm to perform water quantity prediction based on current water consumption, weather information, and holiday information to obtain predicted water consumption. Weather information is information about future weather, that is, information about weather for a period of time in the future. Holiday information may include current holiday information. Holiday information may also include future holiday information. Current holiday information is information about holidays at the current moment. Future holiday information is information about future holidays, that is, information about holidays for a period of time in the future.

[0021] Since the trend of daily water supply changing with time series is relatively stable, the seasonal multivariate autoregressive moving average (SARIMAX) model can be used to predict water consumption, which can improve the accuracy of the prediction results.

[0022] In some embodiments, the server may obtain weather information and holiday information, and may use the SARIMAX model to perform water volume forecasting based on current water consumption, weather information, and holiday information to obtain forecasted water consumption.

[0023] After the server obtains the current water consumption, weather information and holiday information, the current water consumption, weather information and holiday information can be input into the SARIMAX model, and the output of the SARIMAX model is the predicted water consumption.

[0024] SARIMAX is a model that has been pre-trained and verified based on historical water consumption, historical meteorological information, and historical holiday information.

[0025] In addition to the SARIMAX model, the water volume prediction algorithm may also be other algorithms capable of predicting water volume.

[0026] 103. Based on the current water consumption, the predicted water consumption and the current water plant operating condition information, a water pressure scheduling scheme is selected from the scheme library to obtain a first scheme set.

[0027] After the server obtains the predicted water consumption, it can select or search for a water outlet pressure scheduling scheme from the scheme library based on the current water consumption, the predicted water consumption and the current water plant operating condition information to obtain a first scheme set.

[0028] The current water plant operating condition information, that is, the real-time operating condition information of the water plant, is the operating characteristic information of the water plant at the current moment, which may include the information on the operation of the water pump of the current water plant (that is, the start and stop status of the water pump), the value of the current water plant's water outlet flow, the value of the current water plant's water production, the value of the current water plant's water outlet pressure, the value of the water level of the current water plant's water intake well, and other information related to water supply.

[0029] The solution library stores multiple water supply scheduling solutions. These multiple water supply scheduling solutions may include water supply scheduling solutions determined by the user based on historical experience. These multiple water supply scheduling solutions may also include historical water supply scheduling solutions determined according to the water supply scheduling solution determination method. Each water supply scheduling solution may include a water outlet pressure scheduling solution for each water plant and a pump room scheduling solution for each pump room in each water plant.

[0030] The water outlet pressure scheduling scheme may include water plant information and pipe network information. The water plant information may include the value of the water outlet pressure of the water plant, the value of the water outlet flow of the water plant, and other water plant information related to the water supply scheduling of the water plant. The pipe network information may include the value of the pipe network pressure, the value of the pipe network flow, and other network management information related to the water supply scheduling.

[0031] The solution library can be stored in a server or in a dedicated database.

[0032] In some embodiments, the server can determine the predicted water consumption trend based on the predicted water consumption, obtain the current water plant operating condition information, calculate the current water consumption, predicted water consumption trend and current water plant operating condition information, and the similarity between each water supply scheduling scheme in the scheme library (that is, the water outlet pressure scheduling scheme in each water supply scheduling scheme), and then select the water outlet pressure scheduling scheme with a similarity greater than a first threshold from the scheme library, that is, first select the water supply scheduling scheme with a similarity greater than the first threshold from the scheme library, and then select the water outlet pressure scheduling scheme of each water plant from the selected water supply scheduling scheme to obtain a first set of schemes.

[0033] The first scheme set may include one outlet water pressure scheduling scheme or may include multiple outlet water pressure scheduling schemes.

[0034] Since there may be an error between the predicted water consumption predicted by the SARIMAX model and the actual water consumption, such as an error within 3%, directly using the predicted water consumption may not be accurate enough. Therefore, the predicted water consumption trend can be determined based on the predicted water consumption, that is, the changing trend of the predicted water consumption. Using the predicted water consumption trend can improve the accuracy of the water supply scheduling plan.

[0035] It can be seen that the server can accurately obtain the water outlet pressure scheduling scheme with high similarity to the current water consumption, predicted water consumption trend and current water plant operating information from the scheme library, which can improve the accuracy of the final water supply scheduling scheme.

[0036] In some embodiments, multiple water supply scheduling schemes in the scheme library can be classified and stored according to the water plant operating condition information, that is, multiple water supply scheduling schemes are clustered and stored according to the water plant operating condition information. Water supply scheduling schemes of the same type can be stored together and classified into one category. That is, the scheme library can include multiple types of water supply scheduling schemes, and each type of water supply scheduling scheme can include multiple water supply scheduling schemes. The characteristic values ​​of each type of water supply scheduling scheme are different.

[0037] The server can obtain the current water plant operating condition information, calculate the current water consumption, predict the water consumption trend and the current water plant operating condition information, and the similarity between the current water supply scheduling scheme and a water supply scheduling scheme in each type of water supply scheduling scheme in the scheme library, and then select one or more types of water outlet pressure scheduling schemes with a similarity greater than a second threshold from the scheme library to obtain a first scheme set.

[0038] Considering the huge number of water pump combinations, especially the speed-regulating pump combination operating conditions, the historical water supply scheduling plans are stored by clustering the operating conditions to form a plan library. Similar plans can be directly searched, which can reduce repeated calculations and the amount of calculations, thereby improving the efficiency of determining the water supply scheduling plan.

[0039] 104. Based on the first solution set, a genetic annealing algorithm is used to determine a water outlet pressure scheduling solution to obtain a second solution set.

[0040] After the server obtains the first solution set, it can use the genetic annealing algorithm to determine the outlet water pressure scheduling solution based on the first solution set, that is, generate a batch of outlet water pressure scheduling solutions for each water plant to obtain the second solution set.

[0041] The number of the outlet water pressure scheduling schemes included in the first scheme set may be the same as the number of the outlet water pressure scheduling schemes included in the second scheme set.

[0042] The number of water outlet pressure scheduling schemes included in the first scheme set may be different from the number of water outlet pressure scheduling schemes included in the second scheme set. The number of water outlet pressure scheduling schemes included in the first scheme set may be greater than the number of water outlet pressure scheduling schemes included in the second scheme set, or may be less than the number of water outlet pressure scheduling schemes included in the second scheme set.

[0043] Since the genetic annealing algorithm is used, the local optimal solution can be avoided and the accuracy of the final water supply scheduling plan can be improved.

[0044] 105. Based on the second solution set, use the pipeline network hydraulic model to determine the pipeline network information and water plant information to obtain a first result set.

[0045] 106. Based on the first result set, a pump room scheduling solution is selected from the solution library to obtain a third solution set.

[0046] After the server determines the second solution set, it can use the pipeline network hydraulic model to determine the pipeline network information and water plant information based on the second solution set, that is, the outlet water pressure scheduling plan, and obtain the first result set. That is, the solutions in the second solution set are respectively input into the pipeline network hydraulic model, and the set of outputs of the pipeline network hydraulic model is the first result set. The description of the pipeline network information and water plant information can refer to the relevant description above.

[0047] After obtaining the first result set, the server may select a pump room scheduling solution from the solution library based on the first result set to obtain a third solution set.

[0048] The server can calculate the similarity between each result or plan in the first result set and each water supply scheduling plan in the plan library (that is, the pump room scheduling plan in each water supply scheduling plan), and then can select the pump room scheduling plan with a similarity greater than the third threshold from the plan library, that is, the water supply scheduling plan with a similarity greater than the third threshold can be selected from the plan library first, and then the pump room scheduling plan of the pump room of each water plant can be selected from the selected water supply scheduling plan to obtain the third plan set.

[0049] 107. Based on the third solution set, a genetic annealing algorithm is used to determine the pump room scheduling solution to obtain a fourth solution set.

[0050] After the server obtains the third solution set, it can use the genetic annealing algorithm based on the third solution set to determine the pump room scheduling solution, that is, generate a batch of pump room scheduling solutions for each water plant to obtain a fourth solution set.

[0051] The number of pump room scheduling solutions included in the third solution set may be the same as the number of pump room scheduling solutions included in the fourth solution set.

[0052] The number of pump room scheduling solutions included in the third solution set may be different from the number of pump room scheduling solutions included in the fourth solution set. The number of pump room scheduling solutions included in the third solution set may be greater than the number of pump room scheduling solutions included in the fourth solution set, or may be less than the number of pump room scheduling solutions included in the fourth solution set.

[0053] Since the genetic annealing algorithm performs a wash-and-dish optimization on the solutions, the optimization results are used as the initial generation of genes to continue cyclic calculations. The cyclic calculation amount is evaluated based on scheduling variables, expected results, computing performance, etc., which can achieve stable and efficient solution output.

[0054] 108. Based on the first result set and the fourth solution set, a pump room hydraulic model is used to determine a pump room scheduling solution to obtain a second result set.

[0055] After the server determines the fourth solution set, it can use the pump room hydraulic model to determine the pump room scheduling solution based on the first result set and the fourth solution set to obtain the second result set. That is, the corresponding solutions in the first result set and the fourth solution set are respectively input into the pump room hydraulic model, and the set of outputs of the pump room hydraulic model is the second result set.

[0056] The server can determine the pump room scheduling plan using the pump room hydraulic model based on the water plant's water outlet flow value in the first result set, the fourth plan set, and the water level value of the current water plant's water intake well to obtain a second result set.

[0057] The pump room scheduling plan may include information on the operating status of the water pump in the pump room, information on the operating frequency of the water pump, the value of the water outlet pressure of the pump room, the value of the water outlet flow of the pump room, the value of the energy consumption of the pump room (i.e., the pump room energy consumption), and other information related to water supply scheduling in the pump room.

[0058] Since the primary pipe network hydraulic model and the secondary pump room hydraulic model are used, the two-level models can be calculated synchronously, thus greatly improving the efficiency of determining the water supply scheduling plan.

[0059] The server may include multiple processing cores. The pipe network hydraulic model and the pump room hydraulic model may be run by different processing cores so that two-level synchronous calculations can be achieved, which can improve the efficiency of determining the water supply scheduling plan.

[0060] For example, when one processing core determines the water supply scheduling plan for this city, another processing core can determine the water supply scheduling plan for another city, which can improve processing efficiency.

[0061] 109. Based on the first result set, the second result set and the objective function, determine a target water supply scheduling plan.

[0062] After obtaining the second result set, the server may determine a target water supply scheduling plan based on the first result set, the second result set and the objective function.

[0063] The server may first calculate the value of the objective function according to the first result set and the second result set, and finally select the result or plan with the smallest value of the corresponding objective function from the first result set and the second result set to obtain the target water supply scheduling plan.

[0064] Since a complete water supply scheduling plan includes pipeline network information, water plant information and pump room information, the server can first associate the corresponding results or plans in the first result set and the second result set, and then calculate the value of the objective function based on the associated results or plans in the first result set and the results or plans in the second result set.

[0065] One result in the first result set may correspond to multiple results in the second result set, while one result in the second result set corresponds to only one result in the first result set. Therefore, each result in the second result set corresponds to a value of the objective function.

[0066] In addition, the target water supply scheduling scheme determined according to the objective function is the optimal water supply scheduling scheme, that is, the water supply scheduling scheme with the lowest energy consumption, which can reduce the power consumption of water supply scheduling, thereby reducing the operating cost of water supply scheduling and realizing the optimal scheduling of water supply from multiple water sources.

[0067] After the target water supply scheduling scheme is determined, adaptive water supply scheduling can be performed based on the target water supply scheduling scheme.

[0068] exist Figure 1 In the described adaptive scheduling method based on hydraulic model and AI algorithm, the current water consumption and the current water plant operating condition information are used to determine the water supply scheduling plan. Since the real-time water consumption and the real-time water plant operating condition information are used to determine the online water supply scheduling plan, the accuracy of the determined water supply scheduling plan can be improved, thereby improving the safety and stability of water supply scheduling, as well as the accuracy of adaptive water supply scheduling. In addition, since the genetic annealing algorithm is used in the process of determining the water supply scheduling plan, the stability and determination efficiency of the water supply scheduling plan can be improved. Furthermore, the basic water supply data, hydraulic model (i.e., pipe network hydraulic model and pump room hydraulic model) and optimal algorithm (genetic annealing algorithm and objective function) are used, so the accuracy of the water supply scheduling plan can be further improved.

[0069] See also Figure 2 , Figure 2 is a flow chart of another adaptive scheduling method based on a hydraulic model and an AI algorithm disclosed in an embodiment of the present application. The adaptive scheduling method based on a hydraulic model and an AI algorithm can be applied to a server. Figure 2 As shown, the adaptive scheduling method based on hydraulic model and AI algorithm may include the following steps.

[0070] 201. Establish the objective function based on pump room energy consumption, pipe network parameters, water plant parameters and pump room parameters.

[0071] The server can establish an objective function based on the pump room energy consumption, pipe network parameters, water plant parameters and pump room parameters.

[0072] The pipe network parameters may include pipe network pressure, pipe network flow and other pipe network parameters related to water supply scheduling.

[0073] The water plant parameters may include the water plant's outlet pressure, the water plant's outlet flow, and other water plant parameters related to the water supply scheduling of the water plant.

[0074] The pump room parameters may include the operating status of the water pump in the pump room, the operating frequency of the water pump, the water outlet pressure of the pump room, the water outlet flow rate of the pump room, and other parameters of the pump room related to the water supply scheduling of the water plant.

[0075] The server can establish an objective function based on the pump room energy consumption, pipe network parameters, water plant parameters and pump room parameters, that is, the objective function is established with the pump room energy consumption as the target reference and the pipe network parameters, water plant parameters and pump room parameters as boundary conditions.

[0076] The objective function may be a penalty function. When there are values ​​that do not meet the conditions among the values ​​of the pipe network parameters, the values ​​of the water plant parameters, and the values ​​of the pump room parameters, the server may impose a penalty. Exemplarily, when there are values ​​that do not meet the conditions among the values ​​of the pipe network parameters, the values ​​of the water plant parameters, and the values ​​of the pump room parameters, the pump room energy consumption may be penalized, that is, the value of the pump room energy consumption is increased based on the value of the pump room energy consumption in the second result set. The more parameter values ​​that do not meet the conditions, the more the pump room energy consumption value is increased.

[0077] 202. Get the current water consumption.

[0078] The detailed description of step 202 may refer to step 101 .

[0079] 203. Based on the current water consumption, the SARIMAX model is used to predict the water consumption to obtain the predicted water consumption.

[0080] The detailed description of step 203 may refer to step 102 .

[0081] 204. Based on the current water consumption, the predicted water consumption and the current water plant operating condition information, a water pressure scheduling scheme is selected from the scheme library to obtain a first scheme set.

[0082] The detailed description of step 204 may refer to step 103 .

[0083] 205. Based on the first solution set, a genetic annealing algorithm is used to determine a water outlet pressure scheduling solution to obtain a second solution set.

[0084] The detailed description of step 205 may refer to step 104 .

[0085] 206. Based on the second solution set, use the pipeline network hydraulic model to determine the pipeline network information and the water plant information to obtain a first result set.

[0086] 207. Based on the first result set, a pump room scheduling solution is selected from the solution library to obtain a third solution set.

[0087] The detailed description of step 206 - step 207 may refer to step 105 - step 106 .

[0088] 208. Based on the third solution set, a genetic annealing algorithm is used to determine a pump room scheduling solution to obtain a fourth solution set.

[0089] For a detailed description of step 208 , reference may be made to step 107 .

[0090] 209. Determine a pump room scheduling solution using a pump room hydraulic model based on the first result set and the fourth solution set to obtain a second result set.

[0091] The detailed description of step 209 may refer to step 108 .

[0092] 210. Based on the first result set, the second result set and the objective function, determine a target water supply scheduling plan.

[0093] For other detailed descriptions of step 210 , please refer to the relevant descriptions below step 109 .

[0094] 211. Store the target water supply scheduling plan in the plan library.

[0095] After the server determines the target water supply scheduling plan, it can store the target water supply scheduling plan in the plan library for subsequent calls, which can enrich the water supply scheduling plans in the plan library.

[0096] When the plans are stored in a classified manner in the plan library, the server can first determine the category of the target water supply scheduling plan, that is, determine the plan characteristic value of the target water supply scheduling plan through operating condition clustering, and then can assign the target water supply scheduling plan to the corresponding class in the plan library according to the plan characteristic value of the target water supply scheduling plan.

[0097] 212. Send the target water supply scheduling plan to the computer device so that the computer device can perform adaptive water supply scheduling according to the target water supply scheduling plan.

[0098] After the server determines the target water supply scheduling scheme, it can send the target water supply scheduling scheme to the computer device. After the computer device receives the target water supply scheduling scheme from the server, it can perform adaptive water supply scheduling according to the target water supply scheduling scheme.

[0099] The computer device can generate a scheduling instruction according to the target water supply scheduling plan and the current water plant operating condition information, and can perform water supply scheduling according to the scheduling instruction. The computer device can be a device responsible for water supply calling.

[0100] It can be seen that after receiving the target water supply scheduling plan, the computer device does not only perform water supply scheduling according to the target water supply scheduling plan, but also performs water supply scheduling in combination with the current water plant operating information. When the target water supply scheduling plan is the same, the current water plant operating information is different, and the water supply scheduling method may be different, which can improve the flexibility and adaptability of water supply scheduling.

[0101] exist Figure 2In the described adaptive scheduling method based on hydraulic model and AI algorithm, the current water consumption and the current water plant operating condition information are used to determine the water supply scheduling scheme. Since the real-time water consumption and the real-time water plant operating condition information are used to determine the online water supply scheduling scheme, the accuracy of the determined water supply scheduling scheme can be improved, thereby improving the safety and stability of water supply scheduling, as well as the accuracy of adaptive water supply scheduling. In addition, since the genetic annealing algorithm is used in the process of determining the water supply scheduling scheme, the stability and determination efficiency of the water supply scheduling scheme can be improved. Further, the basic water supply data, hydraulic model (i.e., pipe network hydraulic model and pump room hydraulic model) and optimal algorithm (genetic annealing algorithm and objective function) are adopted, so the accuracy of the water supply scheduling scheme can be further improved. Furthermore, the water supply scheduling scheme determined according to the objective function is the water supply scheduling scheme with the lowest energy consumption, which can reduce the power consumption of water supply scheduling, thereby reducing the operating cost of water supply scheduling, and can achieve optimal scheduling of water supply from multiple water sources.

[0102] It should be understood that the same or corresponding information in the above different embodiments can be referenced to each other.

[0103] See also Figure 3 , Figure 3 is a schematic diagram of a structure of an adaptive scheduling device based on a hydraulic model and an AI algorithm disclosed in an embodiment of the present application. The adaptive scheduling device based on a hydraulic model and an AI algorithm can be applied to a server. Figure 3 As shown, the adaptive scheduling device based on hydraulic model and AI algorithm may include: An acquisition unit 301 is used to acquire current water consumption; A prediction unit 302 is used to predict water consumption using a SARIMAX model based on current water consumption to obtain predicted water consumption; A selection unit 303 is used to select a water pressure scheduling scheme from a scheme library based on current water consumption, predicted water consumption and current water plant operating condition information to obtain a first scheme set; A determination unit 304 is configured to determine a water outlet pressure scheduling scheme based on the first scheme set using a genetic annealing algorithm to obtain a second scheme set; The determination unit 304 is further configured to determine the pipe network information and the water plant information using the pipe network hydraulic model based on the second solution set to obtain a first result set; The selection unit 303 is further used to select a pump room scheduling solution from the solution library based on the first result set to obtain a third solution set; The determination unit 304 is further configured to determine the pump room scheduling solution using a genetic annealing algorithm based on the third solution set to obtain a fourth solution set; The determination unit 304 is further used to determine the pump room scheduling solution using the pump room hydraulic model based on the first result set and the fourth solution set to obtain a second result set; The determination unit 304 is further configured to determine a target water supply scheduling scheme based on the first result set, the second result set and the objective function, wherein the target water supply scheduling scheme is used to perform adaptive water supply scheduling.

[0104] In some embodiments, the acquisition unit 301 is further used to acquire weather information and holiday information; The determination unit 304 uses the SARIMAX model to predict water consumption based on the current water consumption, and the predicted water consumption includes: Based on the current water consumption, meteorological information and holiday information, the SARIMAX model is used to predict water consumption and obtain the predicted water consumption.

[0105] In some embodiments, the selection unit 303 is specifically used to: Determine the forecast water use trend based on the forecast water use; Calculate the current water consumption, predicted water consumption trend and current water plant operating information, and the similarity between each water supply scheduling scheme in the scheme library; The outlet water pressure scheduling schemes with similarity greater than a threshold are selected from the scheme library to obtain a first scheme set.

[0106] In some embodiments, the determining unit 304 determines the target water supply scheduling scheme based on the first result set, the second result set and the objective function, including: Calculate the value of the objective function based on the first result set and the second result set; The result with the smallest value of the corresponding objective function is selected from the first result set and the second result set to obtain the target water supply scheduling plan.

[0107] In some embodiments, the adaptive scheduling device based on hydraulic model and AI algorithm may also include: A unit is established for establishing an objective function based on pump room energy consumption, pipe network parameters, water plant parameters and pump room parameters.

[0108] In some embodiments, the adaptive scheduling device based on hydraulic model and AI algorithm may also include: The communication unit is used to send a target water supply scheduling plan to the computer device so that the computer device can perform adaptive water supply scheduling according to the target water supply scheduling plan.

[0109] In some embodiments, the adaptive scheduling device based on hydraulic model and AI algorithm may also include: The storage unit is used to store the target water supply scheduling plan in the plan library.

[0110] Technical personnel in the relevant field can clearly understand that, for the convenience and brevity of description, the specific working processes of the acquisition unit 301, prediction unit 302, selection unit 303, determination unit 304, establishment unit, communication unit and storage unit described above can refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0111] In several embodiments provided in the present application, the coupling between the units may be electrical, mechanical or other forms of coupling.

[0112] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] Please refer to Figure 4 , Figure 4 Schematic diagram of the structure of a server disclosed in the embodiment of the present application. Figure 4 As shown, the server may include a processor 401 and a memory 402. The memory 402 may store one or more computer programs. The one or more computer programs are configured to execute the method described in the above method embodiment. The memory 402 may exist independently or be integrated with the processor 401.

[0114] Processor 401 may include one or more processing cores. Processor 401 may use various interfaces and lines to connect various parts of the entire server, and may execute various functions of the server and process data by running or executing instructions, programs, code sets or instruction sets stored in memory 402, and calling data stored in memory 402. Optionally, processor 401 may be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). Processor 401 may integrate a central processing unit (CPU), etc. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.

[0115] The memory 402 may include a random access memory (RAM) or a read-only memory (ROM). The memory 402 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 402 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function, instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the server during use, etc.

[0116] When the computer program instructions stored in the memory 402 are executed, the processor 401 can be used to execute various operations performed by the server in the above method embodiment. The specific implementation of these operations can refer to the previous embodiments, and will not be repeated here.

[0117] A schematic diagram of the structure of a computer-readable storage medium disclosed in an embodiment of the present application. The computer-readable medium stores computer program code, which can be called by a processor to perform various operations in the above method embodiment. The specific implementation of each of the above operations can be referred to the previous embodiment, and will not be repeated here.

[0118] The computer-readable storage medium may be an electronic memory such as a flash memory, an electrically erasable programmable read only memory (EEPROM), an erasable programmable read only memory (EPROM), a hard disk or a ROM. Alternatively, the computer-readable storage medium may include a non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program codes for executing any method steps in the above method. These computer program codes may be read from or written to one or more computer program products. The computer program codes may be compressed, for example, in an appropriate form.

[0119] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An adaptive scheduling method based on hydraulic model and AI algorithm, characterized in that: include: Get the current water consumption; Based on the current water consumption, a SARIMAX model is used to predict water consumption to obtain predicted water consumption; Based on the current water consumption, the predicted water consumption and the current water plant operating condition information, a water pressure scheduling scheme is selected from a scheme library to obtain a first scheme set; Based on the first solution set, a genetic annealing algorithm is used to determine a water outlet pressure scheduling solution to obtain a second solution set; Based on the second solution set, the pipeline network information and water plant information are determined using the pipeline network hydraulic model to obtain a first result set; Selecting a pump room scheduling solution from the solution library based on the first result set to obtain a third solution set; Determine the pump room scheduling solution based on the third solution set using a genetic annealing algorithm to obtain a fourth solution set; Determine a pump room scheduling solution using a pump room hydraulic model based on the first result set and the fourth solution set to obtain a second result set; A target water supply scheduling scheme is determined based on the first result set, the second result set and an objective function, and the target water supply scheduling scheme is used to perform adaptive water supply scheduling.

2. The method according to claim 1, characterized in that The method further comprises: Get weather information and holiday information; The water consumption is predicted using the SARIMAX model based on the current water consumption to obtain the predicted water consumption, including: Based on the current water consumption, the meteorological information and the holiday information, the SARIMAX model is used to perform water consumption forecasting to obtain the forecasted water consumption.

3. The method according to claim 1, characterized in that The water pressure scheduling scheme is selected from the scheme library based on the current water consumption, the predicted water consumption and the current water plant operating condition information, and the first scheme set includes: Determining a predicted water consumption trend based on the predicted water consumption; Calculate the similarity between the current water consumption, the predicted water consumption trend and the current water plant operating condition information and each water supply scheduling scheme in the scheme library; A water outlet pressure scheduling scheme having a similarity greater than a threshold is selected from the scheme library to obtain a first scheme set.

4. The method according to claim 1, characterized in that: Determining a target water supply scheduling scheme based on the first result set, the second result set and the objective function includes: Calculate the value of the objective function according to the first result set and the second result set; The result with the smallest value of the corresponding objective function is selected from the first result set and the second result set to obtain a target water supply scheduling plan.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: The target water supply scheduling plan is stored in the plan library.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: The objective function is established according to pump room energy consumption, pipe network parameters, water plant parameters and pump room parameters.

7. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: The target water supply scheduling scheme is sent to a computer device so that the computer device performs adaptive water supply scheduling according to the target water supply scheduling scheme.

8. An adaptive scheduling device based on hydraulic model and AI algorithm, characterized in that: include: An acquisition unit, used for acquiring current water consumption; A prediction unit, configured to use a SARIMAX model to predict water consumption based on the current water consumption to obtain predicted water consumption; A selection unit, configured to select a water pressure scheduling scheme from a scheme library based on the current water consumption, the predicted water consumption and the current water plant operating condition information to obtain a first scheme set; A determination unit, configured to determine a water outlet pressure scheduling scheme based on the first scheme set by using a genetic annealing algorithm to obtain a second scheme set; The determining unit is further configured to determine the pipe network information and the water plant information using the pipe network hydraulic model based on the second solution set to obtain a first result set; The selection unit is further configured to select a pump room scheduling solution from the solution library based on the first result set to obtain a third solution set; The determining unit is further used to determine the pump room scheduling scheme based on the third scheme set using a genetic annealing algorithm to obtain a fourth scheme set; The determining unit is further used to determine the pump room scheduling solution using the pump room hydraulic model based on the first result set and the fourth solution set to obtain a second result set; The determination unit is further used to determine a target water supply scheduling scheme based on the first result set, the second result set and the objective function, and the target water supply scheduling scheme is used to perform adaptive water supply scheduling.

9. A server, characterized in that: The method comprises a processor and a memory, wherein the processor is used to call a computer program stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program or a computer instruction. When the computer program or the computer instruction is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images